Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 876 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.5045. Min Act: -0.0000

Data Index: 19720 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.5068. Min Act: -0.0000

Data Index: 511821 (The Pile)

Max Activating Token Index: 873

Text #2

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4632. Min Act: 0.0000

Data Index: 1006717 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1407908 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4352. Min Act: 0.0000

Data Index: 1429453 (The Pile)

Max Activating Token Index: 601

Text #5

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1563883 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1507526 (The Pile)

Max Activating Token Index: 646

Text #7

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4105. Min Act: 0.0000

Data Index: 730440 (The Pile)

Max Activating Token Index: 472

Text #8

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1434822 (The Pile)

Max Activating Token Index: 1001

Text #9

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1564016 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1318154 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3826. Min Act: -0.0000

Data Index: 411862 (The Pile)

Max Activating Token Index: 380

Text #12

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1798644 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3595. Min Act: -0.0000

Data Index: 332284 (The Pile)

Max Activating Token Index: 418

Text #14

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3747. Min Act: -0.0000

Data Index: 309670 (The Pile)

Max Activating Token Index: 127

Text #15

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1949857 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3573. Min Act: -0.0000

Data Index: 819575 (The Pile)

Max Activating Token Index: 45

Text #17

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3569. Min Act: -0.0000

Data Index: 216521 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3635. Min Act: -0.0000

Data Index: 149855 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 0.5068. Min Range: -0.5068

Max Act: 0.3591. Min Act: 0.0000

Data Index: 1589916 (The Pile)

Max Activating Token Index: 130